© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 133770
    Prev
    Next
    INDEX
    Explanations

    want to find

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ពី
    0.39
     depos
    0.38
    AW
    0.38
     डिपॉजिट
    0.38
    getWorld
    0.38
    helia
    0.37
    raut
    0.37
    啉
    0.37
    deposit
    0.37
    ണ്ഡ
    0.37
    POSITIVE LOGITS
     instructing
    0.40
     Commanding
    0.37
     Instruct
    0.37
     Contempor
    0.36
     Instru
    0.36
     जाय
    0.35
    нным
    0.35
    ህ
    0.35
     Config
    0.34
     contended
    0.34
    Activations Density 0.001%

    No Known Activations